AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

Some consistency-related fixes for HunyuanVideo (#10835)

Browse Source 
* update

* update
This commit is contained in:
Aryan
2025-02-21 03:37:07 +05:30
committed by GitHub
parent d9ee3879b0
commit f0707751ef
1 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video.py
View File

@@ -387,7 +387,7 @@ class HunyuanVideoPipeline(DiffusionPipeline, HunyuanVideoLoraLoaderMixin):
def prepare_latents(
self,
batch_size: int,
num_channels_latents: 32,
num_channels_latents: int = 32,
height: int = 720,
width: int = 1280,
num_frames: int = 129,
@@ -402,7 +402,7 @@ class HunyuanVideoPipeline(DiffusionPipeline, HunyuanVideoLoraLoaderMixin):
shape = (
batch_size,
num_channels_latents,
num_frames,
(num_frames - 1) // self.vae_scale_factor_temporal + 1,
int(height) // self.vae_scale_factor_spatial,
int(width) // self.vae_scale_factor_spatial,
)
@@ -624,13 +624,12 @@ class HunyuanVideoPipeline(DiffusionPipeline, HunyuanVideoLoraLoaderMixin):
# 5. Prepare latent variables
num_channels_latents = self.transformer.config.in_channels
num_latent_frames = (num_frames - 1) // self.vae_scale_factor_temporal + 1
latents = self.prepare_latents(
batch_size * num_videos_per_prompt,
num_channels_latents,
height,
width,
num_latent_frames,
num_frames,
torch.float32,
device,
generator,